Design of an Accurate Machine Learning Algorithm to Predict the Binding Energies of Several Adsorbates on Multiple Sites of Metal Surfaces

Machine Learning Prediction of Molecular Binding Profiles on Metal-Porphyrin via Spectroscopic Descriptors

The study of molecular adsorption is crucial for understanding various chemical processes. Spectroscopy offers a convenient and non-invasive way of probing structures of adsorbed states and can be used for real-time observation of molecular binding profiles, including both structural and energetic information. However, deciphering atomic structures from spectral information using the first-principles approach is computationally expensive and time-consuming because of the sophistication of recording spectra, chemical structures, and their relationship. Here, we demonstrate the feasibility of a data-driven machine learning approach for predicting binding energy and structural information directly from vibrational spectra of the adsorbate by using CO adsorption on iron porphyrin as an example. Our trained machine learning model is not only interpretable but also readily transferred to similar metal-nitrogen-carbon systems with comparable accuracy. This work shows the potential of using structure-encoded spectroscopic descriptors in machine learning models for the study of adsorbed states of molecules on transition metal complexes.

CKineticsDB─An Extensible and FAIR Data Management Framework and Datahub for Multiscale Modeling in Heterogeneous Catalysis

A great advantage of computational research is its reproducibility and reusability. However, an enormous amount of computational research data in heterogeneous catalysis is barricaded due to logistical limitations. Sufficient provenance and characterization of data and computational environment, with uniform organization and easy accessibility, can allow the development of software tools for integration across the multiscale modeling workflow. Here, we develop the Chemical Kinetics Database, CKineticsDB, a state-of-the-art datahub for multiscale modeling, designed to be compliant with the FAIR guiding principles for scientific data management. CKineticsDB utilizes a MongoDB back-end for extensibility and adaptation to varying data formats, with a referencing-based data model to reduce redundancy in storage. We have developed a Python software program for data processing operations and with built-in features to extract data for common applications. CKineticsDB evaluates the incoming data for quality and uniformity, retains curated information from simulations, enables accurate regeneration of publication results, optimizes storage, and allows the selective retrieval of files based on domain-relevant catalyst and simulation parameters. CKineticsDB provides data from multiple scales of theory (ab initio calculations, thermochemistry, and microkinetic models) to accelerate the development of new reaction pathways, kinetic analysis of reaction mechanisms, and catalysis discovery, along with several data-driven applications.

The ABC of Generalized Coordination Numbers and Their Use as a Descriptor in Electrocatalysis

The quest for enhanced electrocatalysts can be boosted by descriptor-based analyses. Because adsorption energies are the most common descriptors, electrocatalyst design is largely based on brute-force routines that comb materials databases until an energetic criterion is verified. In this review, it is shown that an alternative is provided by generalized coordination numbers (denoted by CN ¯ $\overline {{\rm{CN}}} $ or GCN), an inexpensive geometric descriptor for strained and unstrained transition metals and some alloys. CN ¯ $\overline {{\rm{CN}}} $ captures trends in adsorption energies on both extended surfaces and nanoparticles and is used to elaborate structure-sensitive electrocatalytic activity plots and selectivity maps. Importantly, CN ¯ $\overline {{\rm{CN}}} $ outlines the geometric configuration of the active sites, thereby enabling an atom-by-atom design, which is not possible using energetic descriptors. Specific examples for various adsorbates (e.g., *OH, *OOH, *CO, and *H), metals (e.g., Pt and Cu), and electrocatalytic reactions (e.g., O₂  reduction, H₂  evolution, CO oxidation, and reduction) are presented, and comparisons are made against other descriptors.

Exploring Structure-Sensitive Relations for Small Species Adsorption Using Machine Learning

Accurate prediction of adsorption energies on heterogeneous catalyst surfaces is crucial to predicting reactivity and screening materials. Adsorption linear scaling relations have been developed extensively but often lack accuracy and apply to one adsorbate and a single binding site type at a time. These facts undermine their ability to predict structure sensitivity and optimal catalyst structure. Using machine learning on nearly 300 density functional theory calculations, we demonstrate that generalized coordination number scaling relations hold well for oxygen- and high-valency carbon-binding species but fail for others. We reveal that the valency and the electronic coupling of a species with the surface, along with the site type and its coordination environment, are critical for small species adsorption. The model simultaneously predicts the adsorption energy and preferred site and significantly outperforms linear scalings in accuracy. It can expose the structure sensitivity of chemical reactions and enable enhanced catalyst activity via engineering particle shape and facet defects. The generality of our methodology is validated by training the model with transition metal data and transferring it to predict adsorption energies on single-atom alloys.

Charting the Atomic C Interaction with Transition Metal Surfaces

Carbon interaction with transition metal (TM) surfaces is a relevant topic in heterogeneous catalysis, either for its poisoning capability, for the recently attributed promoter role when incorporated in the subsurface, or for the formation of early TM carbides, which are increasingly used in catalysis. Herein, we present a high-throughput systematic study, adjoining thermodynamic plus kinetic evidence obtained by extensive density functional calculations on surface models (324 diffusion barriers located on 81 TM surfaces in total), which provides a navigation map of these interactions in a holistic fashion. Correlation between previously proposed electronic descriptors and ad/absorption energies has been tested, with the d-band center being found the most suitable one, although machine learning protocols also underscore the importance of the surface energy and the site coordination number. Descriptors have also been tested for diffusion barriers, with ad/absorption energies and the difference in energy between minima being the most appropriate ones. Furthermore, multivariable, polynomial, and random forest regressions show that both thermodynamic and kinetic data are better described when using a combination of different descriptors. Therefore, looking for a single perfect descriptor may not be the best quest, while combining different ones may be a better path to follow.

A transferable prediction model of molecular adsorption on metals based on adsorbate and substrate properties

Surface adsorption is one of the fundamental processes in numerous fields, including catalysis, the environment, energy and medicine. The development of an adsorption model which provides an effective prediction of binding energy in minutes has been a long term goal in surface and interface science. The solution has been elusive as identifying the intrinsic determinants of the adsorption energy for various compositions, structures and environments is non-trivial. We introduce a new and flexible model for predicting adsorption energies to metal substrates. The model is based on easily computed, intrinsic properties of the substrate and adsorbate, which are the same for all the considered systems. It is parameterised using machine learning based on first-principles calculations of probe molecules (e.g., H₂O, CO₂, O₂, N₂) adsorbed to a range of pure metal substrates. The model predicts the computed dissociative adsorption energy to metal surfaces with a correlation coefficient of 0.93 and a mean absolute error of 0.77 eV for the large database of molecular adsorption energies provided by Catalysis-Hub.org which have a range of 15 eV. As the model is based on pre-computed quantities it provides near-instantaneous estimates of adsorption energies and it is sufficiently accurate to eliminate around 90% of candidates in screening study of new adsorbates. The model, therefore, significantly enhances current efforts to identify new molecular coatings in many applied research fields.

Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis

Autonomous computations that rely on automated reaction network elucidation algorithms may pave the way to make computational catalysis on a par with experimental research in the field. Several advantages of this approach are key to catalysis: (i) automation allows one to consider orders of magnitude more structures in a systematic and open-ended fashion than what would be accessible by manual inspection. Eventually, full resolution in terms of structural varieties and conformations as well as with respect to the type and number of potentially important elementary reaction steps (including decomposition reactions that determine turnover numbers) may be achieved. (ii) Fast electronic structure methods with uncertainty quantification warrant high efficiency and reliability in order to not only deliver results quickly, but also to allow for predictive work. (iii) A high degree of autonomy reduces the amount of manual human work, processing errors, and human bias. Although being inherently unbiased, it is still steerable with respect to specific regions of an emerging network and with respect to the addition of new reactant species. This allows for a high fidelity of the formalization of some catalytic process and for surprising in silico discoveries. In this work, we first review the state of the art in computational catalysis to embed autonomous explorations into the general field from which it draws its ingredients. We then elaborate on the specific conceptual issues that arise in the context of autonomous computational procedures, some of which we discuss at an example catalytic system.

GRAPHICAL ABSTRACT

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11244-021-01543-9.

Adsorption Sites on Pd Nanoparticles Unraveled by Machine-Learning Potential with Adaptive Sampling

Catalytic properties of noble-metal nanoparticles (NPs) are largely determined by their surface morphology. The latter is probed by surface-sensitive spectroscopic techniques in different spectra regions. A fast and precise computational approach enabling the prediction of surface-adsorbate interaction would help the reliable description and interpretation of experimental data. In this work, we applied Machine Learning (ML) algorithms for the task of adsorption-energy approximation for CO on Pd nanoclusters. Due to a high dependency of binding energy from the nature of the adsorbing site and its local coordination, we tested several structural descriptors for the ML algorithm, including mean Pd-C distances, coordination numbers (CN) and generalized coordination numbers (GCN), radial distribution functions (RDF), and angular distribution functions (ADF). To avoid overtraining and to probe the most relevant positions above the metal surface, we utilized the adaptive sampling methodology for guiding the ab initio Density Functional Theory (DFT) calculations. The support vector machines (SVM) and Extra Trees algorithms provided the best approximation quality and mean absolute error in energy prediction up to 0.12 eV. Based on the developed potential, we constructed an energy-surface 3D map for the whole Pd₅₅ nanocluster and extended it to new geometries, Pd₇₉, and Pd₈₅, not implemented in the training sample. The methodology can be easily extended to adsorption energies onto mono- and bimetallic NPs at an affordable computational cost and accuracy.

Electrocatalytic Hydrogenation of Biomass-Derived Organics: A Review

Sustainable energy generation calls for a shift away from centralized, high-temperature, energy-intensive processes to decentralized, low-temperature conversions that can be powered by electricity produced from renewable sources. Electrocatalytic conversion of biomass-derived feedstocks would allow carbon recycling of distributed, energy-poor resources in the absence of sinks and sources of high-grade heat. Selective, efficient electrocatalysts that operate at low temperatures are needed for electrocatalytic hydrogenation (ECH) to upgrade the feedstocks. For effective generation of energy-dense chemicals and fuels, two design criteria must be met: (i) a high H:C ratio via ECH to allow for high-quality fuels and blends and (ii) a lower O:C ratio in the target molecules via electrochemical decarboxylation/deoxygenation to improve the stability of fuels and chemicals. The goal of this review is to determine whether the following questions have been sufficiently answered in the open literature, and if not, what additional information is required:(1)What organic functionalities are accessible for electrocatalytic hydrogenation under a set of reaction conditions? How do substitutions and functionalities impact the activity and selectivity of ECH?(2)What material properties cause an electrocatalyst to be active for ECH? Can general trends in ECH be formulated based on the type of electrocatalyst?(3)What are the impacts of reaction conditions (electrolyte concentration, pH, operating potential) and reactor types?